{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:38Z","timestamp":1778051498698,"version":"3.51.4"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00040","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"328-338","source":"Crossref","is-referenced-by-count":0,"title":["EmojiDiff: Advanced Facial Expression Control with High Identity Preservation in Portrait Generation"],"prefix":"10.1109","author":[{"given":"Liangwei","family":"Jiang","sequence":"first","affiliation":[{"name":"Ant Group,Alipay,Terminal Technology Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruida","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group,Alipay,Terminal Technology Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group,Alipay,Terminal Technology Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Fang","sequence":"additional","affiliation":[{"name":"Ant Group,Alipay,Terminal Technology Department"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenguang","family":"Ma","sequence":"additional","affiliation":[{"name":"Ant Group,Alipay,Terminal Technology Department"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00802"},{"key":"ref4","article-title":"Photoverse: Tuning-free image customization with text-to-image diffusion models","author":"Chen","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_13"},{"key":"ref7","article-title":"Catvton: Concatenation is all you need for virtual try-on with diffusion models","author":"Chong","year":"2024"},{"key":"ref8","year":"2023","journal-title":"Controlnetmediapipeface"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00063"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00812"},{"key":"ref12","volume-title":"FaceFusion","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00238"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00609"},{"key":"ref15","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref16","volume-title":"Blendshapev2","year":"2022"},{"key":"ref17","article-title":"Liveportrait: Efficient portrait animation with stitching and retargeting control","author":"Guo","year":"2024"},{"key":"ref18","article-title":"Pulid: Pure and lightning id customization via contrastive alignment","author":"Guo","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_2"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"ref22","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref23","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Hu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3652557"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"ref26","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01005"},{"key":"ref29","first-page":"2114","article-title":"Towards a simultaneous and granular identity-expression control in per-sonalized face generation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Liu"},{"key":"ref30","article-title":"Facechain: A playground for human-centric artificial intelligence generated content","author":"Liu","year":"2023"},{"key":"ref31","article-title":"Mediapipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref33","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-72913-3_14","article-title":"Arc2face: A foundation model for id-consistent human faces","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Papantoniou"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00237"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02557"},{"key":"ref37","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref38","article-title":"Skyreels-a1: Expressive portrait animation in video diffusion transformers","author":"Qiu","year":"2025"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32729"},{"key":"ref45","article-title":"Gratis: Deep learning graph representation with task-specific topology and multi-dimensional edge features","author":"Song","year":"2022"},{"key":"ref46","article-title":"Towards localized fine-grained control for facial expression generation","author":"Varanka","year":"2024"},{"key":"ref47","article-title":"Instantid: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32877"},{"key":"ref49","article-title":"Aniportrait: Audio-driven synthesis of photorealistic portrait animations","author":"Wei","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"ref51","article-title":"Megactor: Harness the power of raw video for vivid portrait animation","author":"Yang","year":"2024"},{"key":"ref52","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00070"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00669"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01352"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492235.pdf?arnumber=11492235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:14:18Z","timestamp":1778048058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00040","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}